Keras實例：線性迴歸，邏輯迴歸技术頭條網

1.線性迴歸

<code>import numpy as np
 

from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt

# 樣本數據集，第一列為x，第二列為y，在x和y之間建立迴歸模型
data=[
    [0.067732,3.176513],[0.427810,3.816464],[0.995731,4.550095],[0.738336,4.256571],[0.981083,4.560815],
    [0.526171,3.929515],[0.378887,3.526170],[0.033859,3.156393],[0.132791,3.110301],[0.138306,3.149813],
    [0.247809,3.476346],[0.648270,4.119688],[0.731209,4.282233],[0.236833,3.486582],[0.969788,4.655492],
    [0.607492,3.965162],[0.358622,3.514900],[0.147846,3.125947],[0.637820,4.094115],[0.230372,3.476039],
    [0.070237,3.210610],[0.067154,3.190612],[0.925577,4.631504],[0.717733,4.295890],[0.015371,3.085028],
    [0.335070,3.448080],[0.040486,3.167440],[0.212575,3.364266],[0.617218,3.993482],[0.541196,3.891471]
]
#生成X和y矩陣
dataMat = np.array(data)
X = dataMat[:,0:1]   # 變量x
y = dataMat[:,1]   #變量y


# 構建神經網絡模型
model = Sequential()
model.add(Dense(input_dim=1, units=1))

# 選定loss函數和優化器
model.compile(loss='mse', optimizer='sgd')

# 訓練過程
print('Training -----------')
for step in range(501):
    cost = model.train_on_batch(X, y)
    if step % 50 == 0:
        print("After %d trainings, the cost: %f" % (step, cost))

# 測試過程
print('\\nTesting ------------')
cost = model.evaluate(X, y, batch_size=40)
print('test cost:', cost)
W, b = model.layers[0].get_weights()
print('Weights=', W, '\\nbiases=', b)

# 將訓練結果繪出
Y_pred = model.predict(X)
plt.scatter(X, y)
plt.plot(X, Y_pred) 

plt.show()/<code>

2.二分類邏輯迴歸

<code>import numpy as np

from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
import matplotlib.pyplot as plt
from sklearn import datasets

# 樣本數據集，兩個特徵列，兩個分類二分類不需要onehot編碼，直接將類別轉換為0和1，分別代表正樣本的概率。
X,y=datasets.make_classification(n_samples=200, n_features=2, n_informative=2, n_redundant=0,n_repeated=0, n_classes=2, n_clusters_per_class=1)

# 構建神經網絡模型
model = Sequential()
model.add(Dense(input_dim=2, units=1))
model.add(Activation('sigmoid'))

# 選定loss函數和優化器
model.compile(loss='binary_crossentropy', optimizer='sgd')

# 訓練過程
print('Training -----------')
for step in range(501):
    cost = model.train_on_batch(X, y)
    if step % 50 == 0:
        print("After %d trainings, the cost: %f" % (step, cost))

# 測試過程
print('\\nTesting ------------')
cost = model.evaluate(X, y, batch_size=40)
print('test cost:', cost)
W, b = model.layers[0].get_weights()
print('Weights=', W, '\\nbiases=', b)

# 將訓練結果繪出
Y_pred = model.predict(X)
Y_pred = (Y_pred*2).astype('int')  # 將概率轉化為類標號，概率在0-0.5時，轉為0，概率在0.5-1時轉為1
# 繪製散點圖 參數：x橫軸 y縱軸 

plt.subplot(2,1,1).scatter(X[:,0], X[:,1], c=Y_pred)
plt.subplot(2,1,2).scatter(X[:,0], X[:,1], c=y)
plt.show()
/<code>

3.多分類邏輯迴歸

<code>import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
import matplotlib.pyplot as plt
from keras.utils import np_utils
from sklearn import datasets


# 樣本數據集，兩個特徵列，兩個分類二分類不需要onehot編碼，直接將類別轉換為0和1，分別代表正樣本的概率。
X,y=datasets.make_classification(n_samples=200, n_features=2, n_informative=2, n_redundant=0,n_repeated=0, n_classes=3, n_clusters_per_class=1)
n_class=3

# 轉換為one_hot類型
y = np_utils.to_categorical(y, n_class) # 將2分類類標號轉化為one-hot編碼


# 構建神經網絡模型
model = Sequential()
model.add(Dense(input_dim=2, units=n_class))
model.add(Activation('softmax'))

# 選定loss函數和優化器
model.compile(loss='categorical_crossentropy', optimizer='sgd')

# 訓練過程
print('Training -----------')
for step in range(501):
    cost = model.train_on_batch(X, y)
    if step % 50 == 0:
        print("After %d trainings, the cost: %f" % (step, cost))

# 測試過程
print('\\nTesting ------------')
cost = model.evaluate(X, y, batch_size=40)
print('test cost:', cost)
W, b = model.layers[0].get_weights()
print('Weights=', W, '\\nbiases=', b) 


# 將訓練結果繪出
Y_pred = model.predict(X)
Y_pred = Y_pred.argmax(axis=1)   # 獲取概率最大的分類，獲取每行最大值所在的列
print('分類結果：\\n',Y_pred)
# 繪製散點圖 參數：x橫軸 y縱軸
plt.subplot(2,1,1).scatter(X[:,0], X[:,1], c=Y_pred)
plt.subplot(2,1,2).scatter(X[:,0], X[:,1], c=y)
plt.show()/<code>